Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

re: Re: st: Differebnce-in-Difference and Stata

From   "Ariel Linden, DrPH" <>
To   <>
Subject   re: Re: st: Differebnce-in-Difference and Stata
Date   Wed, 8 May 2013 09:20:44 -0400

One of the papers that Austin refers you to below has been published, and I
believe it is slightly different than the earlier version in the link:

BY SUSAN ATHEY AND GUIDO W. IMBENS Econometrica, Vol. 74, No. 2 (March,
2006), 431-497


Date: Tue, 7 May 2013 17:12:37 -0400
From: Austin Nichols <>
Subject: Re: st: Differebnce-in-Difference and Stata

James Bernard <> :
Diff in diff is just a regression with appropriate interaction terms,
and in general you can put any kind of fixed effects in a count model
that you want to. As for diff in diff in a nonlinear model more
generally, the Statalist archives are full of relevant material e.g.
and read
to aid thinking about what specific kind of effect you want to estimate.

On Tue, May 7, 2013 at 10:10 AM, James Bernard <>
> Hi all,
> There is a user written Stata command for Difference-in-Difference
> (DD) by: Villa, Juan M. 2011. DIFF: Stata Module to Perform
> Differences in Differences Estimation. Statistical Software
> Components. Boston College Department of Economics
> It seems like a nice and reliable command, but it is written for a
> linear model. I have two questions:
> 1- Can the logic of DD be applied to non-linear panel models (count
> 2- Does anyone know of a command for a non-linear DD?

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index